Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3492 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9627. Min Range: -9.9627
Max Act: 9.9627. Min Act: -0.1700
Data Index: 3790584 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9627. Min Range: -9.9627
Max Act: 9.8377. Min Act: -0.1700
Data Index: 835493 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9627. Min Range: -9.9627
Max Act: 9.7752. Min Act: -0.1700
Data Index: 345720 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9627. Min Range: -9.9627
Max Act: 9.7127. Min Act: -0.1700
Data Index: 912891 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9627. Min Range: -9.9627
Max Act: 9.6502. Min Act: -0.1700
Data Index: 376624 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9627. Min Range: -9.9627
Max Act: 9.5877. Min Act: -0.1700
Data Index: 2233268 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9627. Min Range: -9.9627
Max Act: 9.5877. Min Act: -0.1700
Data Index: 3558072 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9627. Min Range: -9.9627
Max Act: 9.5877. Min Act: -0.1700
Data Index: 8699904 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9627. Min Range: -9.9627
Max Act: 9.5877. Min Act: -0.1700
Data Index: 2149460 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9627. Min Range: -9.9627
Max Act: 9.5252. Min Act: -0.1700
Data Index: 5369302 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9627. Min Range: -9.9627
Max Act: 9.4002. Min Act: -0.1700
Data Index: 5726895 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9627. Min Range: -9.9627
Max Act: 9.4002. Min Act: -0.1700
Data Index: 4551956 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9627. Min Range: -9.9627
Max Act: 9.4627. Min Act: -0.1700
Data Index: 6591903 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9627. Min Range: -9.9627
Max Act: 9.4627. Min Act: -0.1700
Data Index: 8657839 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9627. Min Range: -9.9627
Max Act: 9.4627. Min Act: -0.1700
Data Index: 8278797 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9627. Min Range: -9.9627
Max Act: 9.4627. Min Act: -0.1700
Data Index: 7485442 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9627. Min Range: -9.9627
Max Act: 9.4002. Min Act: -0.1700
Data Index: 1934771 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9627. Min Range: -9.9627
Max Act: 9.4002. Min Act: -0.1700
Data Index: 2386770 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9627. Min Range: -9.9627
Max Act: 9.4002. Min Act: -0.1699
Data Index: 4723731 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9627. Min Range: -9.9627
Max Act: 9.4627. Min Act: -0.1700
Data Index: 375197 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19